We have 8 of 150 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they often fail to recover once their reasoning enters an erroneous path. Existing test-time fusion methods rely on local fusion signals to determine when to trigger fusion, w...
Large language models (LLMs) have achieved significant advancements in natural language processing tasks, but they remain prone to generating hallucinations—outputs that are logically inconsistent or factually incorrect. While previous research has primarily focused on hallucinations in affirmative contexts, how negate...
Knowledge distillation aims to transfer the factual knowledge of large language models to smaller models for efficient deployment. Yet a teacher may recall a relation in one direction while failing to generate the answer in the reverse direction. Distillation from its generated answers can therefore propagate this dire...
Experimental results show that GLIME significantly improves knowledge generalization in lifelong editing settings while maintaining both editing performance and general capabilities.
Redline is a finite-sample procedure that selects operating points, hand-picked or learned, from the correctness of their answers on calibration prompts, and keeps the reference-relative risk, the joint probability that the reference answers correctly and a candidate configuration does not, within a user-chosen budget...
GLANCE is presented, the first one-pass block drafter that is lossless on an unmodified VLM target, and it breaks the cycle at both ends of a self-defeating cycle.
Because the signal spans a contiguous layer band, LayerMix aggregates it to match oracle-layer performance without oracle access, and characterize the geometry within the controlled paired-example paradigm.
This work shows that training a strong instruction-tuned reasoning model on its own answer-conditioned chains sharply lowers its verifiable-reasoning accuracy, and generates answer-blind data, because no correctness filter can see this damage in the data.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
